Model comparison
Command R+ vs DeepSeek-V3.1-Terminus
DeepSeek-V3.1-Terminus is the stronger model overall, scoring 43.1 to 32.4 on the Noometry Index.
Last verified . 12 shared benchmarks.
Cohere
DeepSeekSummary
- They share 12 benchmarks with published results for both. Command R+ scores higher in 0 categories and DeepSeek-V3.1-Terminus in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where DeepSeek-V3.1-Terminus leads 61.0 to 43.5.
- The biggest single-benchmark swing is DTBench: 54.9% for Command R+ and 81.3% for DeepSeek-V3.1-Terminus.
- DeepSeek-V3.1-Terminus is cheaper at $0.27 / $1 per million input/output tokens, against $2.50 / $10 for Command R+.
- DeepSeek-V3.1-Terminus accepts more context: 164K tokens versus 128K.
Side by side
| Command R+ | DeepSeek-V3.1-Terminus | |
|---|---|---|
| Provider | Cohere | DeepSeek |
| Noometry Index | 32.4 | 43.1 |
| Released | 2024-08-30 | 2025-09-22 |
| Weights | Open | Open |
| Context window | 128K | 164K |
| Max output | 4K | 147K |
| Input $ / M tokens | $2.50 | $0.27 |
| Output $ / M tokens | $10 | $1 |
| Results tracked | 34 | 16 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-V3.1-Terminus leads
Command R+: 29.1 (#309), DeepSeek-V3.1-Terminus: 42.0 (#113)
| Benchmark | Command R+ | DeepSeek-V3.1-Terminus |
|---|---|---|
| LMArena Coding | 1187 | 1426 |
| SciCode | — | 40.6% |
| BigCodeBench Instruct | 33.8% | — |
| LiveBench Coding | 19.1% | — |
| BigCodeBench Complete | 41.9% | — |
| ALE-Bench | — | 745.17 |
| HumanEval+ | 56.7% | — |
| MBPP+ | 63.5% | — |
Reasoning DeepSeek-V3.1-Terminus leads
Command R+: 9.2 (#344), DeepSeek-V3.1-Terminus: 26.4 (#133)
| Benchmark | Command R+ | DeepSeek-V3.1-Terminus |
|---|---|---|
| LMArena Hard Prompts | 1186 | 1426 |
| DTBench | 54.9% | 81.3% |
| LMCA | 5% | 28.6% |
| SimpleBench | 17.4% | — |
| Kagi LLM Benchmark | — | 57.4% |
| CritPt | — | 1.7% |
| LiveBench Reasoning | 24.8% | — |
| LiveBench Data Analysis | 38.1% | — |
| Epoch Capabilities Index | 119.34 | — |
| LiveBench | 31.8% | — |
Math DeepSeek-V3.1-Terminus leads
Command R+: 28.9 (#242), DeepSeek-V3.1-Terminus: 38.5 (#137)
| Benchmark | Command R+ | DeepSeek-V3.1-Terminus |
|---|---|---|
| LMArena Math | 1188 | 1402 |
| LiveBench Math | 21.3% | — |
Knowledge Not comparable
Command R+: 36.4 (#169), DeepSeek-V3.1-Terminus: —
| Benchmark | Command R+ | DeepSeek-V3.1-Terminus |
|---|---|---|
| Vectara Hallucination Rate | 6.9% | — |
| LMArena Expert | 1174 | — |
| MMLU | 69.4% | — |
Multilingual DeepSeek-V3.1-Terminus leads
Command R+: 38.6 (#227), DeepSeek-V3.1-Terminus: 52.1 (#92)
| Benchmark | Command R+ | DeepSeek-V3.1-Terminus |
|---|---|---|
| LMArena Non-English | 1216 | 1407 |
| LMArena Russian | 1227 | 1436 |
| LMArena Chinese | 1226 | — |
| LMArena French | 1209 | — |
| LMArena German | 1216 | — |
| LMArena Japanese | 1166 | — |
| LMArena Korean | 1138 | — |
| LMArena Spanish | 1189 | — |
Instruction Following DeepSeek-V3.1-Terminus leads
Command R+: 60.0 (#254), DeepSeek-V3.1-Terminus: 74.0 (#106)
| Benchmark | Command R+ | DeepSeek-V3.1-Terminus |
|---|---|---|
| LMArena Instruction Following | 1197 | 1404 |
| LiveBench Instruction Following | 57.6% | — |
Long Context DeepSeek-V3.1-Terminus leads
Command R+: 37.3 (#219), DeepSeek-V3.1-Terminus: 43.4 (#97)
| Benchmark | Command R+ | DeepSeek-V3.1-Terminus |
|---|---|---|
| LMArena Longer Query | 1230 | 1421 |
Writing & Preference DeepSeek-V3.1-Terminus leads
Command R+: 43.5 (#228), DeepSeek-V3.1-Terminus: 61.0 (#92)
| Benchmark | Command R+ | DeepSeek-V3.1-Terminus |
|---|---|---|
| LMArena Text | 1229 | 1419 |
| LMArena Creative Writing | 1235 | 1403 |
| LMArena Multi-Turn | 1213 | 1411 |
| LiveBench Language | 29.7% | — |
Frequently asked questions
Is Command R+ better than DeepSeek-V3.1-Terminus?
DeepSeek-V3.1-Terminus is the stronger model overall, scoring 43.1 to 32.4 on the Noometry Index.
Which is cheaper, Command R+ or DeepSeek-V3.1-Terminus?
DeepSeek-V3.1-Terminus is cheaper. It lists at $0.27 per million input tokens and $1 per million output tokens; Command R+ lists at $2.50 and $10.
Is Command R+ or DeepSeek-V3.1-Terminus better for coding?
DeepSeek-V3.1-Terminus scores higher on coding benchmarks: 42.0 versus 29.1 in the Noometry coding category.
Which has the bigger context window?
DeepSeek-V3.1-Terminus does, with 164K tokens against 128K.
How many benchmarks do Command R+ and DeepSeek-V3.1-Terminus share?
12 benchmarks have published results for both models. Command R+ has 34 scored results on Noometry and DeepSeek-V3.1-Terminus has 16.